DeepSeek Reasoner

by DeepSeek · chat

Alias for DeepSeek V4 Flash thinking mode with chain-of-thought reasoning. 1M context, up to 384K output. Top-tier performance on math, code, and complex reasoning.

Pricing

Input: $0.1358/M tokens · Output: $0.2716/M tokens

Capabilities

Function Calling, JSON Mode, Streaming, Reasoning

Context: 1000K tokens

Max output: 384K tokens

Routes: 4/4 healthy

Performance

TTFT: 3988ms · Latency: 50011ms · Throughput: 21.2 tok/s